[FFmpeg-cvslog] avcodec/mpegaudio_tablegen: more dynamic table creation speedups

[Ganesh Ajjanagadde]

ffmpeg | branch: master | Ganesh Ajjanagadde <gajjanagadde at gmail.com> | Fri Nov 27 20:15:42 2015 -0500| [1d0c94ddaef8225c75f72d5d8c54c34270f88d80] | committer: Ganesh Ajjanagadde

avcodec/mpegaudio_tablegen: more dynamic table creation speedups

This further speeds up runtime initialization, with identical generated tables.

Sample benchmark (x86-64, Haswell, GNU/Linux):

old:
34441423 decicycles in mpegaudio_tableinit,    8192 runs,      0 skips

new:
10776291 decicycles in mpegaudio_tableinit,    8192 runs,      0 skips

Most low hanging fruit is taken care of here. For some idea, note that
83,064 array elements totalling 233,722 bytes need to be initialized.
Thus, with this patch, we average ~ 12.9 cycles per element or ~ 4.6
cycles per byte.

Reviewed-by: Derek Buitenhuis <derek.buitenhuis at gmail.com>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=1d0c94ddaef8225c75f72d5d8c54c34270f88d80
---

 libavcodec/mpegaudio_tablegen.h |   22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/libavcodec/mpegaudio_tablegen.h b/libavcodec/mpegaudio_tablegen.h
index dd67a09..1b27314 100644
--- a/libavcodec/mpegaudio_tablegen.h
+++ b/libavcodec/mpegaudio_tablegen.h
@@ -45,23 +45,28 @@ static float expval_table_float[512][16];
 static av_cold void mpegaudio_tableinit(void)
 {
     int i, value, exponent;
-    double exp2_lut[4] = {
+    static const double exp2_lut[4] = {
         1.00000000000000000000, /* 2 ^ (0 * 0.25) */
         1.18920711500272106672, /* 2 ^ (1 * 0.25) */
         M_SQRT2               , /* 2 ^ (2 * 0.25) */
         1.68179283050742908606, /* 2 ^ (3 * 0.25) */
     };
-    double cbrt_lut[16];
+    static double pow43_lut[16];
+    double exp2_base = 2.11758236813575084767080625169910490512847900390625e-22; // 2^(-72)
+    double exp2_val;
+    double pow43_val = 0;
     for (i = 0; i < 16; ++i)
-        cbrt_lut[i] = cbrt(i);
+        pow43_lut[i] = i * cbrt(i);
 
     for (i = 1; i < TABLE_4_3_SIZE; i++) {
-        double value = i / 4;
         double f, fm;
         int e, m;
-        f  = value / IMDCT_SCALAR * cbrt(value) * exp2_lut[i & 3];
+        double value = i / 4;
+        if (i & 3 == 0)
+            pow43_val = value / IMDCT_SCALAR * cbrt(value);
+        f  = pow43_val * exp2_lut[i & 3];
         fm = frexp(f, &e);
-        m  = (uint32_t)(fm * (1LL << 31) + 0.5);
+        m  = llrint(fm * (1LL << 31));
         e += FRAC_BITS - 31 + 5 - 100;
 
         /* normalized to FRAC_BITS */
@@ -69,8 +74,11 @@ static av_cold void mpegaudio_tableinit(void)
         table_4_3_exp[i]   = -e;
     }
     for (exponent = 0; exponent < 512; exponent++) {
+        if (exponent && exponent & 3 == 0)
+            exp2_base *= 2;
+        exp2_val = exp2_base * exp2_lut[exponent & 3] / IMDCT_SCALAR;
         for (value = 0; value < 16; value++) {
-            double f = value * cbrt_lut[value] * pow(2, (exponent - 400) * 0.25 + FRAC_BITS + 5) / IMDCT_SCALAR;
+            double f = pow43_lut[value] * exp2_val;
             expval_table_fixed[exponent][value] = (f < 0xFFFFFFFF ? llrint(f) : 0xFFFFFFFF);
             expval_table_float[exponent][value] = f;
         }